codex-gpt-5.4 [high]
Blind track
2.39/4
Overall
6
Families scored
18
Seeds
0
Infra errors
±0.52
Std error
Per-task family scores
Failure-level histogram
L0 (failed L1)0
L1 structural9
L2 geometric2
L3 physical constraints2
L4 dfm5
infra error0
Efficiency & cost
| Metric | Value | Source |
|---|---|---|
| Agent calls | 1.00 | runtime.agent_call_count |
| Wall time (s) | 116.75 | runtime.wall_time_s |
| Cost (USD) | 0.11 (est.) | api_equivalent_estimate |
| Total tokens | 31427.94 (est.) | local_log_tokens |
Perception track
2.31/4
Overall
6
Families scored
18
Seeds
0
Infra errors
±0.49
Std error
Per-task family scores
Failure-level histogram
L0 (failed L1)0
L1 structural9
L2 geometric2
L3 physical constraints3
L4 dfm4
infra error0
Efficiency & cost
| Metric | Value | Source |
|---|---|---|
| Agent calls | 2.11 | runtime.agent_call_count |
| Wall time (s) | 164.08 | runtime.wall_time_s |
| Cost (USD) | 0.14 (est.) | api_equivalent_estimate |
| Total tokens | 52335.44 (est.) | local_log_tokens |
Perception summary
| Observations | 20 |
| Compiled | 20 |
| Render artifacts | 60 |
| Section artifacts | 120 |
| Warnings | 1 |
| Mean iterations | 2.11 |